implement-plan

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.70). The required workflow instructs the agent to run /council and /best-practices-research on the “plan attached to this message” (and its touched domains), which implies the LLM will ingest free-form text from an externally provided plan and potentially fetch/analyze public domain content at runtime.